Enhancing Community Well-being Through Public Transport Accessibility¶

SCENARIO
  • As a public health researcher, I want to analyze the impact of public transport accessibility on the health and well-being of Melbourne residents.

Public transport can significantly influence people's access to health services, social connections, and overall quality of life. This analysis aims to identify how proximity to bus and tram stops correlates with various well-being indicators, such as physical and mental health.

  • As a city planner, I want to understand the relationship between public transport access and community participation.

Community participation can be facilitated by convenient public transport options, allowing residents to engage in social activities, work, and leisure. This analysis will help in planning public transport routes to enhance community connectivity.

What this use case will teach you
At the end of this use case you will:
  • Learn how to import and integrate data from multiple sources, including survey data and geospatial data.
  • Understand methods for geocoding and calculating distances between locations.
  • Gain skills in analyzing and visualizing the relationship between public transport accessibility and community well-being indicators.
  • Be able to present findings that can influence public policy and urban planning decisions.
Introduction or background relating to problem

Public transport plays a crucial role in urban settings, offering accessibility and mobility to residents. For a city like Melbourne, which is known for its high quality of life, understanding the role of public transport in enhancing community well-being is vital. This analysis seeks to explore how close proximity to bus and tram stops influences residents' physical health, mental well-being, social connections, and participation in community activities.

Key Factors of Analysis

  • Physical Health: How does public transport accessibility impact access to healthcare services and physical activity levels?
  • Mental Well-being: Is there a correlation between easy access to public transport and reduced stress or improved mental health?
  • Community Participation: Does proximity to public transport encourage participation in social and community activities?
  • Social Connectedness: How does public transport influence social interactions and connections?

DATASETS :

  • Dataset 1: https://data.melbourne.vic.gov.au/explore/dataset/social-indicators-for-city-of-melbourne-residents-2023/information/ Title: Social Indicators for City of Melbourne Residents 2023 (CoMSIS) Source: City of Melbourne Open Data Portal Description: This dataset provides comprehensive social and demographic data for Melbourne residents, including health, well-being, and transport-related information.

  • Dataset 2: https://data.melbourne.vic.gov.au/explore/dataset/bus-stops/information/ Title: Bus Stops Source: City of Melbourne Open Data Portal Description: This dataset contains the location of bus stops within the city of Melbourne.

  • Dataset 3: : https://data.melbourne.vic.gov.au/explore/dataset/tram-tracks/export/ Title: Tram Stops Source: City of Melbourne Open Data Portal Description: This dataset contains the location of tram stops within the city of Melbourne.

  • PART-1 DOWNLOADING DATASETS
  • PART-2 DATA CLEANING
  • PART-3 DATA INTEGRATION
  • PART-4 EXPLORATIVE DATA ANALYSIS
  • Part-5 STATISTICAL AND SPATIAL ANALYSIS
  • PART-6 VISUALIZATION AND ANALYSIS OF PUBLIC TRANSPORT ACCESSIBILITY AND ITS IMPACT ON HEALTH OUTCOMES
  • Part-7 RECOMMENDATIONS
indicator type topic description response respondent_group year sample_size result format
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 25-34 years 2023 419 17.1 per cent
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 45-54 years 2023 128 15.0 per cent
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 65+ years 2023 202 3.6 per cent
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally docklands 3008 2023 113 4.5 per cent
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally melbourne 3000 2023 338 18.0 per cent
... ... ... ... ... ... ... ... ... ... ...
495 6a other food security worried food would run out yes, in the last 12 months melbourne 3000 2023 341 25.1 per cent
496 6a other food security worried food would run out yes, in the last 12 months parkville 3052 2023 77 20.1 per cent
497 6a other food security worried food would run out yes, in the last 12 months south yarra 3141 / melbourne/st kilda road 3004 2023 138 28.2 per cent
498 6b other food security skipped meals yes, in the last 12 months 18-24 years 2023 273 32.0 per cent
499 6b other food security skipped meals yes, in the last 12 months kensington / flemington 3031 2023 89 9.0 per cent

500 rows × 10 columns

social_indicators_df.head(500)
indicator type topic description response year sample_size result format age_group location
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 419 17.1 per cent 25-34 years None
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 128 15.0 per cent 45-54 years None
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 202 3.6 per cent 65+ years None
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 113 4.5 per cent None docklands 3008
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 338 18.0 per cent None melbourne 3000
... ... ... ... ... ... ... ... ... ... ... ...
495 6a other food security worried food would run out yes, in the last 12 months 2023 341 25.1 per cent None melbourne 3000
496 6a other food security worried food would run out yes, in the last 12 months 2023 77 20.1 per cent None parkville 3052
497 6a other food security worried food would run out yes, in the last 12 months 2023 138 28.2 per cent None south yarra 3141 / melbourne/st kilda road 3004
498 6b other food security skipped meals yes, in the last 12 months 2023 273 32.0 per cent 18-24 years None
499 6b other food security skipped meals yes, in the last 12 months 2023 89 9.0 per cent None kensington / flemington 3031

500 rows × 11 columns

social_indicators_df.head(594)
indicator type topic description response year sample_size result format age_group location latitude longitude
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 419 17.1 per cent 25-34 years None 44.933143 7.540121
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 128 15.0 per cent 45-54 years None 44.933143 7.540121
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 202 3.6 per cent 65+ years None 44.933143 7.540121
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 113 4.5 per cent None docklands 3008 -37.817542 144.939492
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 338 18.0 per cent None melbourne 3000 -37.814245 144.963173
... ... ... ... ... ... ... ... ... ... ... ... ... ...
589 9 other quality of life satisfaction with life as a whole average satisfaction score (from 0-100) 2023 202 80.6 average 65+ years None 44.933143 7.540121
590 9 other quality of life satisfaction with life as a whole average satisfaction score (from 0-100) 2023 192 69.3 average None carlton 3053 -37.800423 144.968434
591 9 other quality of life satisfaction with life as a whole average satisfaction score (from 0-100) 2023 1369 72.7 average None city of melbourne -37.812382 144.948265
592 9 other quality of life satisfaction with life as a whole average satisfaction score (from 0-100) 2023 69 78.7 average None east melbourne 3002 -37.812498 144.985885
593 9 other quality of life satisfaction with life as a whole average satisfaction score (from 0-100) 2023 89 74.0 average None kensington / flemington 3031 -37.788559 144.931535

594 rows × 13 columns

 

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 309 entries, 0 to 308
Data columns (total 16 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   geo_point_2d  309 non-null    object 
 1   geo_shape     309 non-null    object 
 2   prop_id       309 non-null    int64  
 3   addresspt1    309 non-null    float64
 4   addressp_1    309 non-null    int64  
 5   asset_clas    309 non-null    object 
 6   asset_type    309 non-null    object 
 7   objectid      309 non-null    int64  
 8   str_id        309 non-null    int64  
 9   addresspt     309 non-null    int64  
 10  asset_subt    0 non-null      float64
 11  model_desc    309 non-null    object 
 12  mcc_id        309 non-null    int64  
 13  roadseg_id    309 non-null    int64  
 14  descriptio    309 non-null    object 
 15  model_no      309 non-null    object 
dtypes: float64(2), int64(7), object(7)
memory usage: 38.8+ KB
geo_point_2d geo_shape prop_id addresspt1 addressp_1 asset_clas asset_type objectid str_id addresspt asset_subt model_desc mcc_id roadseg_id descriptio model_no
0 -37.80384165792465, 144.93239283833262 {"coordinates": [144.93239283833262, -37.80384... 0 76.819824 357 Signage Sign - Public Transport 355 1235255 570648 NaN Sign - Public Transport 1 Panel 1235255 21673 Sign - Public Transport 1 Panel Bus Stop Type 13 P.16
1 -37.81548699581418, 144.9581794249902 {"coordinates": [144.9581794249902, -37.815486... 0 21.561304 83 Signage Sign - Public Transport 600 1231226 548056 NaN Sign - Public Transport 1 Panel 1231226 20184 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
2 -37.81353897396532, 144.95728334230756 {"coordinates": [144.95728334230756, -37.81353... 0 42.177187 207 Signage Sign - Public Transport 640 1237092 543382 NaN Sign - Public Transport 1 Panel 1237092 20186 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
3 -37.82191394843844, 144.95539345270072 {"coordinates": [144.95539345270072, -37.82191... 0 15.860434 181 Signage Sign - Public Transport 918 1232777 103975 NaN Sign - Public Transport 1 Panel 1232777 22174 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
4 -37.83316401267591, 144.97443745130263 {"coordinates": [144.97443745130263, -37.83316... 0 0.000000 0 Signage Sign - Public Transport 1029 1271914 0 NaN Sign - Public Transport 1 Panel 1271914 22708 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
295 -37.830076314348155, 144.96531772571083 {"coordinates": [144.96531772571083, -37.83007... 0 16.382280 121 Signage Sign - Public Transport 40427 1239220 110628 NaN Sign - Public Transport 1 Panel 1239220 22118 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
296 -37.82097678869638, 144.92581314868238 {"coordinates": [144.92581314868238, -37.82097... 0 77.355590 154 Signage Sign - Public Transport 40450 1245195 562527 NaN Sign - Public Transport 1 Panel 1245195 22156 Sign - Public Transport 1 Panel Bus Stop Type 3 P.16
297 -37.796717481892664, 144.94652849185758 {"coordinates": [144.94652849185758, -37.79671... 0 14.595037 215 Signage Sign - Public Transport 40643 1249762 565421 NaN Sign - Public Transport 1 Panel 1249762 20907 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
298 -37.84536002766068, 144.982312412603 {"coordinates": [144.982312412603, -37.8453600... 0 0.000000 0 Signage Sign - Public Transport 41418 1255285 0 NaN Sign - Public Transport 1 Panel 1255285 22308 Sign - Public Transport 1 Panel Bus Stop Type 8 P.16
299 -37.80136463912211, 144.91440645303163 {"coordinates": [144.91440645303163, -37.80136... 0 9.334432 19 Signage Sign - Public Transport 41465 1463005 654920 NaN Sign - Public Transport 1 Panel 1463005 21683 Sign - Public Transport 1 Panel Bus Stop Type 3 P.16

300 rows × 16 columns



<class 'pandas.core.frame.DataFrame'>
RangeIndex: 645 entries, 0 to 644
Data columns (total 6 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   description    645 non-null    object 
 1   name           645 non-null    object 
 2   latitude       645 non-null    float64
 3   longitude      645 non-null    float64
 4   geo_shape_lat  645 non-null    float64
 5   geo_shape_lon  645 non-null    float64
dtypes: float64(4), object(2)
memory usage: 30.4+ KB
None
description name latitude longitude geo_shape_lat geo_shape_lon
0 Attributes< kml_3 -37.788613 144.934616 144.934525 -37.788621
1 Attributes< kml_5 -37.819186 144.961035 144.960994 -37.819175
2 Attributes< kml_6 -37.818380 144.959453 144.959344 -37.818227
3 Attributes< kml_7 -37.814404 144.970251 144.969150 -37.814700
4 Attributes< kml_8 -37.816739 144.969909 144.970083 -37.816716
... ... ... ... ... ... ...
640 Attributes< kml_622 -37.811666 144.956372 144.956422 -37.811691
641 Attributes< kml_626 -37.811041 144.958897 144.959070 -37.811019
642 Attributes< kml_629 -37.810688 144.960102 144.959047 -37.810969
643 Attributes< kml_641 -37.832398 144.971967 144.971857 -37.832174
644 Attributes< kml_644 -37.821467 144.969274 144.969284 -37.821401

645 rows × 6 columns
indicator type topic description response year sample_size result format age_group location latitude longitude nearest_bus_stop_distance nearest_tram_stop_distance accessibility bus_stop_travel_time tram_stop_travel_time
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 419 17.1 per cent 25-34 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 128 15.0 per cent 45-54 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 202 3.6 per cent 65+ years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 113 4.5 per cent None docklands 3008 -37.817542 144.939492 6.446944e+02 3.411385e+02 Very Good 7.736333e+01 4.093662e+01
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 338 18.0 per cent None melbourne 3000 -37.814245 144.963173 2.291950e+02 2.736518e+00 Very Good 2.750340e+01 3.283822e-01
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
295 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 89 18.1 per cent None kensington / flemington 3031 -37.788559 144.931535 1.760548e+02 5.733400e+01 Very Good 2.112658e+01 6.880079e+00
296 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 344 36.5 per cent None melbourne 3000 -37.814245 144.963173 2.291950e+02 2.736518e+00 Very Good 2.750340e+01 3.283822e-01
297 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 77 29.5 per cent None parkville 3052 -37.787115 144.951553 6.527690e+02 6.612698e+02 Very Good 7.833229e+01 7.935238e+01
298 6a other food security worried food would run out yes, in the last 12 months 2023 420 24.4 per cent 25-34 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
299 6a other food security worried food would run out yes, in the last 12 months 2023 69 15.5 per cent None east melbourne 3002 -37.812498 144.985885 7.815369e+02 3.530502e+02 Very Good 9.378442e+01 4.236602e+01

300 rows × 18 columns
indicator type topic description response year sample_size result format age_group location latitude longitude nearest_bus_stop_distance nearest_tram_stop_distance accessibility bus_stop_travel_time tram_stop_travel_time
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 419 17.1 per cent 25-34 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 128 15.0 per cent 45-54 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 202 3.6 per cent 65+ years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 113 4.5 per cent None docklands 3008 -37.817542 144.939492 6.446944e+02 3.411385e+02 Very Good 7.736333e+01 4.093662e+01
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 338 18.0 per cent None melbourne 3000 -37.814245 144.963173 2.291950e+02 2.736518e+00 Very Good 2.750340e+01 3.283822e-01
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
295 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 89 18.1 per cent None kensington / flemington 3031 -37.788559 144.931535 1.760548e+02 5.733400e+01 Very Good 2.112658e+01 6.880079e+00
296 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 344 36.5 per cent None melbourne 3000 -37.814245 144.963173 2.291950e+02 2.736518e+00 Very Good 2.750340e+01 3.283822e-01
297 6 council plan indicator food security experienced food insecurity (worried food woul... yes, in the last 12 months 2023 77 29.5 per cent None parkville 3052 -37.787115 144.951553 6.527690e+02 6.612698e+02 Very Good 7.833229e+01 7.935238e+01
298 6a other food security worried food would run out yes, in the last 12 months 2023 420 24.4 per cent 25-34 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06
299 6a other food security worried food would run out yes, in the last 12 months 2023 69 15.5 per cent None east melbourne 3002 -37.812498 144.985885 7.815369e+02 3.530502e+02 Very Good 9.378442e+01 4.236602e+01

300 rows × 18 columns

DATA VERIFICATION AND QUALITY CHECK(after integration) 

 

Missing values in each column:
 indicator                       0
type                            0
topic                           0
description                     0
response                        0
year                            0
sample_size                     0
result                          0
format                          0
age_group                     396
location                      198
latitude                        0
longitude                       0
nearest_bus_stop_distance       0
nearest_tram_stop_distance      0
accessibility                   0
bus_stop_travel_time            0
tram_stop_travel_time           0
dtype: int64

EXPLORATIVE DATA ANALYSIS

The primary goal here is to gain an initial understanding of the data, uncover patterns, and identify relationships between variables that can help guide further analysis.

  • Descriptive Statistics for Distance and Travel Time: This section provides basic summary statistics for the columns related to the distance to bus/tram stops and travel times.
  • Distribution of Distances to the Nearest Bus Stop:This part includes the visualization of the distribution of distances to the nearest bus stop using a histogram.
  • Relationship Between Bus Stop Distance and Well-being Indicator: This section visualizes the relationship between the distance to the nearest bus stop and the well-being indicator using a scatter plot.
  • Geographical Map of Respondent Locations: Here, I am visualizing the geographical distribution of respondents using their latitude and longitude data with Folium maps.
  • Categorizing Distance to Public Transport:categorizing the distance into classes like "Very Close," "Moderate," and "Far" for both bus and tram stop distances.
  • Converting Categorical Data to Numerical Data: Here we use label encoding to convert categorical columns (distance categories) into numerical values for analysis
  • Correlation Analysis of Transport Accessibility and Well-being Indicators:In this part, we calculate the correlation matrix between the numeric columns (distances, travel times, and distance categories) and visualize it using a heatmap.


Descriptive statistics:
        nearest_bus_stop_distance  nearest_tram_stop_distance  \
count               5.940000e+02                5.940000e+02   
mean                8.576338e+06                8.576792e+06   
std                 7.786932e+06                7.787432e+06   
min                 1.247726e+02                2.736518e+00   
25%                 6.527690e+02                3.530502e+02   
50%                 1.449454e+07                1.449805e+07   
75%                 1.641019e+07                1.641037e+07   
max                 1.693035e+07                1.693056e+07   

       bus_stop_travel_time  tram_stop_travel_time  
count          5.940000e+02           5.940000e+02  
mean           1.029161e+06           1.029215e+06  
std            9.344319e+05           9.344918e+05  
min            1.497271e+01           3.283822e-01  
25%            7.833229e+01           4.236602e+01  
50%            1.739345e+06           1.739766e+06  
75%            1.969222e+06           1.969245e+06  
max            2.031642e+06           2.031667e+06
No description has been provided for this image
No description has been provided for this image 
latitude      57
longitude     57
location     198
dtype: int64
Make this Notebook Trusted to load map: File -> Trust Notebook
indicator type topic description response year sample_size result format age_group location latitude longitude nearest_bus_stop_distance nearest_tram_stop_distance accessibility bus_stop_travel_time tram_stop_travel_time bus_distance_category tram_distance_category
0 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 419 17.1 per cent 25-34 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06 Far Far
1 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 128 15.0 per cent 45-54 years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06 Far Far
2 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 202 3.6 per cent 65+ years None 44.933143 7.540121 1.641019e+07 1.641037e+07 Poor 1.969222e+06 1.969245e+06 Far Far
3 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 113 4.5 per cent None docklands 3008 -37.817542 144.939492 6.446944e+02 3.411385e+02 Very Good 7.736333e+01 4.093662e+01 Moderate Very Close
4 18 other health smoking behaviour reported as smoke daliy or smoke occassionally 2023 338 18.0 per cent None melbourne 3000 -37.814245 144.963173 2.291950e+02 2.736518e+00 Very Good 2.750340e+01 3.283822e-01 Very Close Very Close 


Correlation Matrix:
                             nearest_bus_stop_distance  \
nearest_bus_stop_distance                    1.000000   
nearest_tram_stop_distance                   1.000000   
bus_stop_travel_time                         1.000000   
tram_stop_travel_time                        1.000000   
bus_distance_category                       -0.799394   
tram_distance_category                      -0.845644   
nearest_tram_stop_distance                   1.000000   

                            nearest_tram_stop_distance  bus_stop_travel_time  \
nearest_bus_stop_distance                     1.000000              1.000000   
nearest_tram_stop_distance                    1.000000              1.000000   
bus_stop_travel_time                          1.000000              1.000000   
tram_stop_travel_time                         1.000000              1.000000   
bus_distance_category                        -0.799400             -0.799394   
tram_distance_category                       -0.845653             -0.845644   
nearest_tram_stop_distance                    1.000000              1.000000   

                            tram_stop_travel_time  bus_distance_category  \
nearest_bus_stop_distance                1.000000              -0.799394   
nearest_tram_stop_distance               1.000000              -0.799400   
bus_stop_travel_time                     1.000000              -0.799394   
tram_stop_travel_time                    1.000000              -0.799400   
bus_distance_category                   -0.799400               1.000000   
tram_distance_category                  -0.845653               0.929972   
nearest_tram_stop_distance               1.000000              -0.799400   

                            tram_distance_category  nearest_tram_stop_distance  
nearest_bus_stop_distance                -0.845644                    1.000000  
nearest_tram_stop_distance               -0.845653                    1.000000  
bus_stop_travel_time                     -0.845644                    1.000000  
tram_stop_travel_time                    -0.845653                    1.000000  
bus_distance_category                     0.929972                   -0.799400  
tram_distance_category                    1.000000                   -0.845653  
nearest_tram_stop_distance               -0.845653                    1.000000
No description has been provided for this image

STATISTICAL AND SPATIAL ANALYSIS

This section explores the relationships between public transport accessibility and well-being indicators, using both statistical and spatial analysis techniques. The key components of the analysis include:

  • Correlation Analysis: We compute the correlation matrix to understand the relationships between the distances to public transport (bus stops and tram stops) and the well-being indicators.
  • Regression Analysis: A linear regression model is fitted to examine the influence of distance to bus and tram stops on a well-being indicator.
  • ANOVA (Analysis of Variance): We use ANOVA to test if the mean distance to public transport varies significantly across different age groups.
  • Clustering Analysis: KMeans clustering is applied to group respondents based on their proximity to public transport.
  • Spatial Analysis: Moran's I test is performed to examine spatial autocorrelation, and maps are created to visualize the geographic distribution of distances to public transport.
  • Geospatial Mapping: A folium map is created to visualize the spatial distribution of bus and tram stop distances, with customized colors based on distance proximity.
No description has been provided for this image 
 

/opt/miniconda3/envs/MelbourneCityOpenData/lib/python3.8/site-packages/sklearn/cluster/_kmeans.py:1412: FutureWarning:

The default value of `n_init` will change from 10 to 'auto' in 1.4. Set the value of `n_init` explicitly to suppress the warning
No description has been provided for this image 


/opt/miniconda3/envs/MelbourneCityOpenData/lib/python3.8/site-packages/libpysal/weights/weights.py:224: UserWarning: The weights matrix is not fully connected: 
 There are 13 disconnected components.
  warnings.warn(message)
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Make this Notebook Trusted to load map: File -> Trust Notebook

italicized text VISUALIZATION AND ANALYSIS OF PUBLIC TRANSPORT ACCESSIBILITY AND ITS IMPACT ON HEALTH OUTCOMES

  • Creating maps visualizing the distribution of public transport stops and areas with varying levels of accessibility.

    • Data Preparation and Handling
      • Checking and Handling Empty Datasets
      • Converting DataFrames to GeoDataFrames
    • Creating Maps
      • Creating Interactive Maps with Folium
      • Adding Bus Stops to the Map
      • Adding Tram Stops to the Map
      • Adding Health Data to the Map
    • Creating Static Maps
      • Plotting with GeoPandas and Matplotlib

  • Analysis and Visualization

    • Summary Statistics of Health Outcomes by Accessibility Level
    • Plot Health Outcomes by Accessibility
    • Average Distances to Public Transport by Age Group
      • Plot Average Bus Stop Distance by Age Group
      • Plot Average Tram Stop Distance by Age Group
    • Scatter Plots of Distance vs. Accessibility
      • Scatter Plot of Bus Stop Distance vs. Accessibility
      • Scatter Plot of Tram Stop Distance vs. Accessibility

  • Overlaying these maps with demographic and health data in socail indicators to identify potential disparities.
Make this Notebook Trusted to load map: File -> Trust Notebook
No description has been provided for this image
No description has been provided for this image 


     age_group  avg_bus_distance  avg_tram_distance
0  18-24 years      1.641019e+07       1.641037e+07
1  25-34 years      1.641019e+07       1.641037e+07
2  35-44 years      1.641019e+07       1.641037e+07
3  45-54 years      1.641019e+07       1.641037e+07
4  55-64 years      1.641019e+07       1.641037e+07
5    65+ years      1.641019e+07       1.641037e+07
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
No description has been provided for this image
Make this Notebook Trusted to load map: File -> Trust Notebook

RECOMMENDATIONS

  • Identify Areas with Poor Transport Accessibility
    • Caluculating the accessibility Scores : calculates an accessibility score based on the inverse of the combined distances to the nearest bus and tram stops
    • Identify Areas with Poor Accessibility : filters the dataset to identify areas where the accessibility score is below a certain threshold, indicating poor accessibility to public transport. The threshold is set at 0.3, which helps isolate regions that might require targeted improvements.
    • Merging with Health Data and Analyzing Correlations : merges the data on poor accessibility with health indicators, then analyzes correlations between distances to bus and tram stops and life satisfaction. A regression analysis is performed to evaluate the relationship between accessibility and health metrics, providing insights into how transport access influences well-being
    • Visualizations
      • Scatter Plot for Bus Stop Distance vs. Life Satisfaction : visualizes the relationship between bus stop distance and life satisfaction, helping to identify trends and patterns in the data.
      • Box Plot for Life Satisfaction Across Accessibility Categories : displays life satisfaction scores across different accessibility categories, revealing variations in well-being related to accessibility levels
    • Correlation and Visual Inspection : calculates the correlation between accessibility scores and health indicators, and visualizes the relationship using a scatter plot to further explore these connections.
  • Recommendations Based on Accessibility and Health Scores : Recommendations are generated based on accessibility and health scores. The logic behind the recommendations is explained, and a DataFrame is created to provide clear and actionable suggestions for improving public transport accessibility and health outcomes
  • Visualizing Recommendations on a Map : visualizes the recommendations on a map using Folium. Markers are added to represent areas with poor accessibility and corresponding recommendations, providing a spatial view of suggested improvements.
No description has been provided for this image
No description has been provided for this image
Make this Notebook Trusted to load map: File -> Trust Notebook
Make this Notebook Trusted to load map: File -> Trust Notebook

CONCLUSION/RESULTS :

In this analysis, I examined the relationship between public transport accessibility and various health and well-being indicators. By integrating geospatial data with social indicators, we identified areas with poor accessibility and assessed their impact on health outcomes.

The key findings include:

  • Accessibility Disparities: Areas with lower accessibility scores were identified, indicating a need for targeted interventions to improve public transport infrastructure.
  • Health Outcomes: Correlations between transport accessibility and health metrics were analyzed, revealing significant associations that highlight the importance of addressing accessibility issues to improve overall well-being.
  • Recommendations: Based on the analysis, specific recommendations were provided to enhance public transport services and address accessibility gaps, including expanding transport routes and increasing service frequency in underserved areas.

The recommendations provided aim to:

  • Enhance Accessibility: Improve public transport infrastructure and services in areas with poor accessibility to ensure that all residents have equitable access to essential services.
  • Improve Health Outcomes: Address disparities in health outcomes by promoting better access to transportation, which can positively impact various aspects of health and well-being.
  • Guide Policy and Planning: Inform urban planning and policy decisions by highlighting areas where targeted improvements can have the most significant impact.

REFERENCES USED: https://pypi.org/project/shapely/ https://pypi.org/project/geopandas/ https://pyproj4.github.io/pyproj/stable/ https://pandas.pydata.org/docs/index.html

DATASETS USED:

  • https://data.melbourne.vic.gov.au/explore/dataset/social-indicators-for-city-of-melbourne-residents-2023/information/
  • https://data.melbourne.vic.gov.au/explore/dataset/bus-stops/information/
  • https://data.melbourne.vic.gov.au/explore/dataset/tram-tracks/export/